All new accounts created on Gitlab now require administrator approval. If you invite any collaborators, please let Flux staff know so they can approve the accounts.

hugetlbpage.c 7.81 KB
Newer Older
Steve Capper's avatar
Steve Capper committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
/*
 * arch/arm64/mm/hugetlbpage.c
 *
 * Copyright (C) 2013 Linaro Ltd.
 *
 * Based on arch/x86/mm/hugetlbpage.c.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>

int pmd_huge(pmd_t pmd)
{
32
	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
Steve Capper's avatar
Steve Capper committed
33 34 35 36
}

int pud_huge(pud_t pud)
{
37
#ifndef __PAGETABLE_PMD_FOLDED
38
	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
39 40 41
#else
	return 0;
#endif
Steve Capper's avatar
Steve Capper committed
42 43
}

44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
			   pte_t *ptep, pte_t pte, size_t *pgsize)
{
	pgd_t *pgd = pgd_offset(mm, addr);
	pud_t *pud;
	pmd_t *pmd;

	*pgsize = PAGE_SIZE;
	if (!pte_cont(pte))
		return 1;
	if (!pgd_present(*pgd)) {
		VM_BUG_ON(!pgd_present(*pgd));
		return 1;
	}
	pud = pud_offset(pgd, addr);
	if (!pud_present(*pud)) {
		VM_BUG_ON(!pud_present(*pud));
		return 1;
	}
	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd)) {
		VM_BUG_ON(!pmd_present(*pmd));
		return 1;
	}
	if ((pte_t *)pmd == ptep) {
		*pgsize = PMD_SIZE;
		return CONT_PMDS;
	}
	return CONT_PTES;
}

void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
			    pte_t *ptep, pte_t pte)
{
	size_t pgsize;
	int i;
	int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize);
	unsigned long pfn;
	pgprot_t hugeprot;

	if (ncontig == 1) {
		set_pte_at(mm, addr, ptep, pte);
		return;
	}

	pfn = pte_pfn(pte);
	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
	for (i = 0; i < ncontig; i++) {
		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
			 pte_val(pfn_pte(pfn, hugeprot)));
		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
		ptep++;
		pfn += pgsize >> PAGE_SHIFT;
		addr += pgsize;
	}
}

pte_t *huge_pte_alloc(struct mm_struct *mm,
		      unsigned long addr, unsigned long sz)
{
	pgd_t *pgd;
	pud_t *pud;
	pte_t *pte = NULL;

	pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz);
	pgd = pgd_offset(mm, addr);
	pud = pud_alloc(mm, pgd, addr);
	if (!pud)
		return NULL;

	if (sz == PUD_SIZE) {
		pte = (pte_t *)pud;
	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
		pmd_t *pmd = pmd_alloc(mm, pud, addr);

		WARN_ON(addr & (sz - 1));
		/*
		 * Note that if this code were ever ported to the
		 * 32-bit arm platform then it will cause trouble in
		 * the case where CONFIG_HIGHPTE is set, since there
		 * will be no pte_unmap() to correspond with this
		 * pte_alloc_map().
		 */
127
		pte = pte_alloc_map(mm, pmd, addr);
128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300
	} else if (sz == PMD_SIZE) {
		if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) &&
		    pud_none(*pud))
			pte = huge_pmd_share(mm, addr, pud);
		else
			pte = (pte_t *)pmd_alloc(mm, pud, addr);
	} else if (sz == (PMD_SIZE * CONT_PMDS)) {
		pmd_t *pmd;

		pmd = pmd_alloc(mm, pud, addr);
		WARN_ON(addr & (sz - 1));
		return (pte_t *)pmd;
	}

	pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr,
	       sz, pte, pte_val(*pte));
	return pte;
}

pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd = NULL;
	pte_t *pte = NULL;

	pgd = pgd_offset(mm, addr);
	pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd);
	if (!pgd_present(*pgd))
		return NULL;
	pud = pud_offset(pgd, addr);
	if (!pud_present(*pud))
		return NULL;

	if (pud_huge(*pud))
		return (pte_t *)pud;
	pmd = pmd_offset(pud, addr);
	if (!pmd_present(*pmd))
		return NULL;

	if (pte_cont(pmd_pte(*pmd))) {
		pmd = pmd_offset(
			pud, (addr & CONT_PMD_MASK));
		return (pte_t *)pmd;
	}
	if (pmd_huge(*pmd))
		return (pte_t *)pmd;
	pte = pte_offset_kernel(pmd, addr);
	if (pte_present(*pte) && pte_cont(*pte)) {
		pte = pte_offset_kernel(
			pmd, (addr & CONT_PTE_MASK));
		return pte;
	}
	return NULL;
}

pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
			 struct page *page, int writable)
{
	size_t pagesize = huge_page_size(hstate_vma(vma));

	if (pagesize == CONT_PTE_SIZE) {
		entry = pte_mkcont(entry);
	} else if (pagesize == CONT_PMD_SIZE) {
		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
	} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
		pr_warn("%s: unrecognized huge page size 0x%lx\n",
			__func__, pagesize);
	}
	return entry;
}

pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
			      unsigned long addr, pte_t *ptep)
{
	pte_t pte;

	if (pte_cont(*ptep)) {
		int ncontig, i;
		size_t pgsize;
		pte_t *cpte;
		bool is_dirty = false;

		cpte = huge_pte_offset(mm, addr);
		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
		/* save the 1st pte to return */
		pte = ptep_get_and_clear(mm, addr, cpte);
		for (i = 1; i < ncontig; ++i) {
			/*
			 * If HW_AFDBM is enabled, then the HW could
			 * turn on the dirty bit for any of the page
			 * in the set, so check them all.
			 */
			++cpte;
			if (pte_dirty(ptep_get_and_clear(mm, addr, cpte)))
				is_dirty = true;
		}
		if (is_dirty)
			return pte_mkdirty(pte);
		else
			return pte;
	} else {
		return ptep_get_and_clear(mm, addr, ptep);
	}
}

int huge_ptep_set_access_flags(struct vm_area_struct *vma,
			       unsigned long addr, pte_t *ptep,
			       pte_t pte, int dirty)
{
	pte_t *cpte;

	if (pte_cont(pte)) {
		int ncontig, i, changed = 0;
		size_t pgsize = 0;
		unsigned long pfn = pte_pfn(pte);
		/* Select all bits except the pfn */
		pgprot_t hugeprot =
			__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
				 pte_val(pte));

		cpte = huge_pte_offset(vma->vm_mm, addr);
		pfn = pte_pfn(*cpte);
		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
					  *cpte, &pgsize);
		for (i = 0; i < ncontig; ++i, ++cpte) {
			changed = ptep_set_access_flags(vma, addr, cpte,
							pfn_pte(pfn,
								hugeprot),
							dirty);
			pfn += pgsize >> PAGE_SHIFT;
		}
		return changed;
	} else {
		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
	}
}

void huge_ptep_set_wrprotect(struct mm_struct *mm,
			     unsigned long addr, pte_t *ptep)
{
	if (pte_cont(*ptep)) {
		int ncontig, i;
		pte_t *cpte;
		size_t pgsize = 0;

		cpte = huge_pte_offset(mm, addr);
		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
		for (i = 0; i < ncontig; ++i, ++cpte)
			ptep_set_wrprotect(mm, addr, cpte);
	} else {
		ptep_set_wrprotect(mm, addr, ptep);
	}
}

void huge_ptep_clear_flush(struct vm_area_struct *vma,
			   unsigned long addr, pte_t *ptep)
{
	if (pte_cont(*ptep)) {
		int ncontig, i;
		pte_t *cpte;
		size_t pgsize = 0;

		cpte = huge_pte_offset(vma->vm_mm, addr);
		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
					  *cpte, &pgsize);
		for (i = 0; i < ncontig; ++i, ++cpte)
			ptep_clear_flush(vma, addr, cpte);
	} else {
		ptep_clear_flush(vma, addr, ptep);
	}
}

Steve Capper's avatar
Steve Capper committed
301 302 303
static __init int setup_hugepagesz(char *opt)
{
	unsigned long ps = memparse(opt, &opt);
304

Steve Capper's avatar
Steve Capper committed
305 306 307 308
	if (ps == PMD_SIZE) {
		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
	} else if (ps == PUD_SIZE) {
		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
309 310 311 312
	} else if (ps == (PAGE_SIZE * CONT_PTES)) {
		hugetlb_add_hstate(CONT_PTE_SHIFT);
	} else if (ps == (PMD_SIZE * CONT_PMDS)) {
		hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
Steve Capper's avatar
Steve Capper committed
313
	} else {
314
		hugetlb_bad_size();
315
		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
Steve Capper's avatar
Steve Capper committed
316 317 318 319 320
		return 0;
	}
	return 1;
}
__setup("hugepagesz=", setup_hugepagesz);
321 322 323 324 325 326 327 328 329 330

#ifdef CONFIG_ARM64_64K_PAGES
static __init int add_default_hugepagesz(void)
{
	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
		hugetlb_add_hstate(CONT_PMD_SHIFT);
	return 0;
}
arch_initcall(add_default_hugepagesz);
#endif